Why Agentic Systems Need Ontologies — Frank Coyle, UC Berkeley - YouTube
youtube.com · 3,462 words · saved by 1 readers
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
A second refund on the same order. A payout sent to the support desk instead of the buyer. An order status of "probably shipped." These are the kinds of mistakes a probabilistic agent makes and a paragraph of instructions cannot reliably stop. Frank Coyle argues that most agent failures, from brittle tools to fragile handoffs, are symptoms of one missing layer: a formal ontology sitting outside the model as logical guardrails. LLMs reason probabilistically over domains they only half understand, and no amount of prompt engineering closes that gap. His fix is neurosymbolic: probabilistic…
saved by
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Agent Ontologies - by Philippe Page - Mainframeblog.mainfra.me
- Don’t Build Multi-Agents | Cognitioncognition.ai
- Full Walkthrough: Workflow for AI Coding — Matt Pocockyoutube.com
- Don’t Outsource Your Thinkingteltam.github.io
- How AI is Changing Programmingyoutube.com
- How We Build Effective Agents: Barry Zhang, Anthropicyoutube.com
- Designing agentic loopssimonwillison.net
- Andrew Ng Explores The Rise Of AI Agents And Agentic Reasoning | BUILD 2024 Keynoteyoutube.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Agent Harness for Learning Thingsyoutube.com